Co-Initialization of Control Filter and Secondary Path via Meta-Learning for Active Noise Control

TL;DR

This paper introduces a meta-learning approach to initialize control filters and secondary paths in active noise control systems, significantly improving early performance and adaptability in changing environments.

Contribution

It proposes a MAML-based co-initialization method for ANC that enhances quick adaptation without altering the runtime algorithm.

Findings

Lower early-stage error in ANC

Shorter time-to-target for noise reduction

Faster recovery after environment changes

Abstract

Active noise control (ANC) must adapt quickly when the acoustic environment changes, yet early performance is largely dictated by initialization. We address this with a Model-Agnostic Meta-Learning (MAML) co-initialization that jointly sets the control filter and the secondary-path model for FxLMS-based ANC while keeping the runtime algorithm unchanged. The initializer is pre-trained on a small set of measured paths using short two-phase inner loops that mimic identification followed by residual-noise reduction, and is applied by simply setting the learned initial coefficients. In an online secondary path modeling FxLMS testbed, it yields lower early-stage error, shorter time-to-target, reduced auxiliary-noise energy, and faster recovery after path changes than a baseline without re-initialization. The method provides a simple fast start for feedforward ANC under environment changes, requiring a small set of paths to pre-train.